Patent Application
20120054414
This application claims the benefit of People's Republic of China application Serial No. 201010271335.9, filed Sep. 1, 2010, the subject matter of which is incorporated herein by reference.
The present invention relates to a solid state drive, and more particularly to a data control method of a solid state drive.
As is well known, a solid state drive (SSD) is a data storage device that uses a NAND flash memory to store data. The NAND flash memory is a non-volatile memory. After data are written to the NAND flash memory, if no power is supplied to the flash memory, the data are still retained in the flash memory.
Generally, the flash memory 105 comprises many blocks. Each block consists of a number of pages (or sectors), for example 64 pages. Each page is typically 4K bytes in size. Due to the inherent properties of the flash memory 105, the writing operation is performed in a page at a time, and the erasing operation is performed in a block-wise fashion.
Generally, each block of the flash memory 105 has limited erase count. For prolonging the service life of the flash memory 105, a wear leveling technique is disclosed. According to the wear leveling technique, the writing operations across all available blocks of the flash memory 105 are balanced in order to prevent overuse of specified blocks (high erase counts) and occurrence of bad blocks. In such way, the service life of the flash memory 105 may be prolonged.
For performing the wear leveling operation, the conventional solid state drive 10 uses the controlling unit 101 to detect the erase count of each block of the flash memory 105 and exchange data between the high-erase-count block and the low-erase-count block.
Moreover, after many times of writing and reading operations, each block of the flash memory 105 may contain valid pages and invalid pages. The data of the valid pages can be read out again. Whereas, the data of the invalid pages are no longer available.
Since the erasing operation of the flash memory 105 is performed in a block-wise fashion, the block containing the valid pages cannot be erased by the controlling unit 101. For effectively managing the data of each block, a garbage collection algorithm is provided. The garbage collection algorithm is a process of collecting valid pages of an old block and rewriting the valid pages into another new block. After the valid pages are collected, the old block may be erased and reused. Generally, the old block having a lower erase count will be preferentially erased. In addition, when the number of valid pages is lower than a threshold value, the garbage collection will be performed again.
From the above discussions, it is found that the erase count of each block needs to be detected by the controlling unit 101 of the solid state drive 10. In addition, the erase count of each block is used as an index. According to the index, the controlling unit 101 will determine whether the wear leveling operation or the garbage collection is performed.
Recently, as the size of the semiconductor is gradually reduced, the size of each memory cell of the flash memory 105 is downsized to 30 nm. After the data are written into the flash memory 105 for a time period (e.g. shorter than 3 months), the stored data of the memory cell are possibly lost.
Therefore, the object of the present invention is to provide a data control method of a solid state drive. The data control method uses a time parameter as an index to perform data loss prevention, so that the possibly-lost data are moved to a new block to prevent data loss. In addition, according to the time parameter serving as the index, either the wear leveling operation or the garbage collection is performed.
The present invention provides a solid state drive. The solid state drive includes a flash memory and a controlling unit. The flash memory includes plural blocks. Each block includes plural pages. The controlling unit is in communication with the flash memory. When data of a specified block are erased or data are written into the specified block, the controlling unit provides a time parameter to the specified block. The controlling unit performs a data loss prevention, a wear leveling operation or a garbage collection according to the time parameter.
The present invention also provides a data control method of a flash memory. The flash memory includes plural blocks. Each block includes plural pages. The data control method includes the following steps. When data of the specified block are erased or data are written into the specified block, a time parameter is provided to the specified block. Then, a data loss prevention, a wear leveling operation or a garbage collection is performed according to the time parameter.
The above objects and advantages of the present invention will become more readily apparent to those ordinarily skilled in the art after reviewing the following detailed descriptions and accompanying drawings, in which:
The present invention will now be described more specifically with reference to the following embodiments. It is to be noted that the following descriptions of preferred embodiments of this invention are presented herein for purpose of illustration and description only. It is not intended to be exhaustive or to be limited to the precise form disclosed.
In an embodiment, the controlling unit 501 may provide a time parameter. In addition, the time signal T generated by the real time clock component 503 is used as the time parameter. For example, the time parameter is a time information including year, month, day, hour, minute and second. Of course, the time parameter will increase progressively without being zeroed. When data stored in any block of the flash memory 505 are erased or data are written into any block of the flash memory 505, the time parameter corresponding to the block will be recorded in the block by the controlling unit 501. The time parameter of the block is retrieved by the controlling unit 501 for a data loss prevention, a wear leveling operation or a garbage collection, which will be described later.
According to the time parameter stored in each block of the flash memory 505 and the current time parameter, the controlling unit 501 performs data loss prevention. Since the data are possibly lost after they have been written into the flash memory 505 for a time period (e.g. 3 months), the controlling unit 501 may judge whether the data of an old block needs to be moved to a new block according to a difference between the current time parameter and the time parameter of the old block.
Since the data of the first block have been written into the second block and the time parameter corresponding to the second block is the current time parameter, the possibility of losing data of the second block is minimized. In addition, after the data have been written into the second block, the data of the first block become invalid data. Meanwhile, the erasing operation may be performed on the first block.
Please refer to
In a case that no data are stored in the fourth block (e.g. the fourth block is a blank block that has been erased), the data of the third block are directly written into the fourth block to implement the wear leveling operation (Step S403). The time parameter of the fourth block is changed to the current time parameter. In addition, after the data have been written into the fourth block, the data of the third block become invalid data. Meanwhile, the erasing operation may be performed on the third block.
Whereas, in a case that the fourth block contains data, the data of the third block and the data of the fourth block are exchanged to implement the wear leveling operation (Step S403). The time parameters of the third block and fourth block are changed to the current time parameter.
Please refer to
After the process of performing the garbage collection on the fifth block is completed, the data of the fifth block become invalid data. Meanwhile, the fifth block may be erased and reused.
From the above descriptions, the time parameter corresponding to each block is used as an index, and a data loss prevention, a wear leveling operation or a garbage collection is performed according to the index. In the prior art, only the erase count is used as the index. Whereas, according to the data control method of the present invention, the wear leveling operation or the garbage collection may be performed without the need of using the erase count as the index.
In the above embodiments, the time signal T generated by the real time clock component 503 is used as the time parameter. Nevertheless, the way of acquiring the time parameter is not restricted to the time signal T. Hereinafter, some other approaches of acquiring the time parameter will be illustrated.
For example, when a file is written to the solid state drive 50, the information of the file is also transmitted from the host 52 to the controlling unit 501. The information of the file includes the writing time of the file. The writing time of the file may be retrieved by the controlling unit 501 to be used as the time parameter. In other words, when a file is written from the host 52 to the solid state drive 50 through the external bus 60, the controlling unit 501 will use the writing time of the file as the time parameter, and then count up time. Therefore, when data stored in any block of the flash memory 505 are erased or data are written into any block of the flash memory 505, the time parameter corresponding to the block will be recorded in the block by the controlling unit 501. The time parameter is also retrieved by the controlling unit 501. According to the time parameter, the controlling unit 501 performs a data loss prevention, a wear leveling operation or a garbage collection.
Moreover, the host 52 is in communication with the solid state drive 50 according to a communication protocol, so that a time signal may be transmitted from the host 52 to the solid state drive 50 via the communication protocol. The controlling unit 501 may acquire the time parameter according to the time signal outputted from the host 52, and then count up time. According to the time parameter, the controlling unit 501 performs a data loss prevention, a wear leveling operation or a garbage collection.
Moreover, in a case that no time signal is acquired by the controlling unit 501, the controlling unit 501 may count the total erase count of the flash memory 505. That is, once one block of the flash memory 505 is erased, the time parameter is automatically increased by a value “1”. If the total erase count of all blocks of the flash memory 505 is 1,500, the time parameter is 1,500.
According to undue experiments, if the difference between the time parameter corresponding to a specified block and the current time parameter is 200, the data have been written into the specified block for more than 2.5 months. As a consequence, if the controlling unit 501 judges that the time difference between the time parameter of a specified block and the current time parameter is greater than 200, the data loss prevention is performed on the specified block. Similarly, according to the lowest time parameter of the specified block, the wear leveling operation or the garbage collection may be performed on the specified block.
From the above descriptions, the present invention provides a data control method of a flash memory. By using a time parameter as an index, a data loss prevention, a wear leveling operation or a garbage collection may be performed
While the invention has been described in terms of what is presently considered to be the most practical and preferred embodiments, it is to be understood that the invention needs not be limited to the disclosed embodiment. On the contrary, it is intended to cover various modifications and similar arrangements included within the spirit and scope of the appended claims which are to be accorded with the broadest interpretation so as to encompass all such modifications and similar structures.
| Number | Date | Country | Kind |
|---|---|---|---|
| 201010271335.9 | Sep 2010 | CN | national |
